Restarts subject to approximate sharpness: A parameter-free and optimal scheme for first-order methods

5 January 2023

Papers citing "Restarts subject to approximate sharpness: A parameter-free and optimal scheme for first-order methods"

5 / 5 papers shown

Title
Learning smooth functions in high dimensions: from sparse polynomials to deep neural networks Ben Adcock Simone Brugiapaglia N. Dexter S. Moraga 42 4 0 04 Apr 2024
Implicit regularization in AI meets generalized hardness of approximation in optimization -- Sharp results for diagonal linear networks J. S. Wind Vegard Antun A. Hansen 25 4 0 13 Jul 2023
Acceleration Methods Alexandre d’Aspremont Damien Scieur Adrien B. Taylor 173 119 0 23 Jan 2021
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition Hamed Karimi J. Nutini Mark W. Schmidt 139 1,201 0 16 Aug 2016
A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights Weijie Su Stephen P. Boyd Emmanuel J. Candes 108 1,154 0 04 Mar 2015